Topology-Aware Spatio-Temporal Graph Transformer for Predicting Smart Grid Failures

TL;DR

This paper presents a novel topology-aware spatio-temporal graph transformer that significantly improves failure prediction accuracy in smart grids by integrating physical network topology and temporal data into an end-to-end model.

Contribution

The study introduces a new transformer architecture that incorporates physical grid topology and temporal PMU data for more accurate failure prediction in smart grids.

Findings

Achieved perfect recall (1.000) and high F1-score (0.858) in failure prediction.

Outperformed baseline models like XGBoost in accuracy and F1-score.

Demonstrated the model's potential for critical infrastructure monitoring and maintenance.

Abstract

Smart grid infrastructure needs improved resilience and preventive maintenance through more accurate predictions. Current methodologies lack accurate representation of spatio-temporal-causal interdependencies and class imbalance in failure prediction tasks. This study introduces a Topology-Aware Spatio-Temporal Graph Transformer (ST-GT) architecture that overcomes existing limitations by using three main innovations: (1) directly incorporating physical transmission network topology into the transformer attention mechanism to identify spatial failure propagation patterns; (2) unified processing of static topological descriptors and (3) temporal Phasor Measurement Units (PMU) sequences in an end-to-end framework. The ST-GT model exhibited outstanding performance in five-fold cross-validation across 10 substations, attaining perfect recall (1.000 $\pm$ 0.001) and an F1-score of 0.858 $\pm$ 0.009, markedly surpassing XGBoost baselines (0.683 accuracy/F1). Perfect recall guarantees that no critical failures are overlooked, which is essential for grid safety; however, it may lead to an increase in false alarm rates. This framework integrates temporal dynamics modeling with spatial graph awareness for critical infrastructure monitoring. It offers interpretable insights into failure propagation pathways and enhances maintenance strategies. Future research focuses on developing cost-weighted loss functions for precision-recall trade-off enhancement, implementing real-time monitoring systems with uncertainty quantification, and creating cost-sensitive frameworks balancing false alarm expenditures with failure consequences. The methodology success suggests its potential for wider application in critical infrastructure areas requiring spatial temporal failure prediction.